© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 28626
    Prev
    Next
    INDEX
    Explanations

    need to know

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ga
    -0.07
     sie
    -0.07
    比较多
    -0.07
    检查
    -0.07
    国家标准
    -0.06
    試
    -0.06
    わけです
    -0.06
    Ł
    -0.06
     offshore
    -0.06
    .gz
    -0.06
    POSITIVE LOGITS
    .setLayoutParams
    0.08
    .TRAN
    0.07
     Anaheim
    0.07
    (decimal
    0.07
    andWhere
    0.07
    _REPLY
    0.06
    护肤品
    0.06
    _InitStructure
    0.06
    !!.
    0.06
    读后
    0.06
    Activations Density 0.019%

    No Known Activations